A survey of multi-objective sequential decision-making

DM Roijers, P Vamplew, S Whiteson… - Journal of Artificial …, 2013‏ - jair.org
Sequential decision-making problems with multiple objectives arise naturally in practice and
pose unique challenges for research in decision-theoretic planning and learning, which has …

Decision-theoretic planning: Structural assumptions and computational leverage

C Boutilier, T Dean, S Hanks - Journal of Artificial Intelligence Research, 1999‏ - jair.org
Planning under uncertainty is a central problem in the study of automated sequential
decision making, and has been addressed by researchers in many different fields, including …

Partially observable markov decision processes in robotics: A survey

M Lauri, D Hsu, J Pajarinen - IEEE Transactions on Robotics, 2022‏ - ieeexplore.ieee.org
Noisy sensing, imperfect control, and environment changes are defining characteristics of
many real-world robot tasks. The partially observable Markov decision process (POMDP) …

[ספר][B] Partially observed Markov decision processes

V Krishnamurthy - 2016‏ - books.google.com
Covering formulation, algorithms, and structural results, and linking theory to real-world
applications in controlled sensing (including social learning, adaptive radars and sequential …

A survey of point-based POMDP solvers

G Shani, J Pineau, R Kaplow - Autonomous Agents and Multi-Agent …, 2013‏ - Springer
The past decade has seen a significant breakthrough in research on solving partially
observable Markov decision processes (POMDPs). Where past solvers could not scale …

Planning and acting in partially observable stochastic domains

LP Kaelbling, ML Littman, AR Cassandra - Artificial intelligence, 1998‏ - Elsevier
In this paper, we bring techniques from operations research to bear on the problem of
choosing optimal actions in partially observable stochastic domains. We begin by …

The complexity of decentralized control of Markov decision processes

DS Bernstein, R Givan, N Immerman… - Mathematics of …, 2002‏ - pubsonline.informs.org
We consider decentralized control of Markov decision processes and give complexity
bounds on the worst-case running time for algorithms that find optimal solutions …

[PDF][PDF] Point-based value iteration: An anytime algorithm for POMDPs

J Pineau, G Gordon, S Thrun - Ijcai, 2003‏ - fore.robot.cc
(PBVI) algorithm for POMDP planning. PBVI approximates an exact value iteration solution
by selecting a small set of representative belief points and then tracking the value and its …

[PDF][PDF] Dynamic programming for partially observable stochastic games

EA Hansen, DS Bernstein, S Zilberstein - AAAI, 2004‏ - cdn.aaai.org
We develop an exact dynamic programming algorithm for partially observable stochastic
games (POSGs). The algorithm is a synthesis of dynamic programming for partially …

Online planning algorithms for POMDPs

S Ross, J Pineau, S Paquet, B Chaib-Draa - Journal of Artificial Intelligence …, 2008‏ - jair.org
Abstract Partially Observable Markov Decision Processes (POMDPs) provide a rich
framework for sequential decision-making under uncertainty in stochastic domains …